公开(公告)号：US20240267568A1

公开(公告)日：2024-08-08

申请号：US18639170

申请日：2024-04-18

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Ahmet Burakhan Koyuncu ,  Han Gao ,  Atanas Boev ,  Elena Alexandrovna Alshina

IPC: H04N19/91 ,  G06V10/44 ,  G06V10/82

CPC classification number: H04N19/91 ,  G06V10/44 ,  G06V10/82

Abstract: Methods and apparatuses are described for entropy encoding and decoding of a latent tensor, which includes separating the latent tensor into segments in the spatial dimensions, each segment including at least one latent tensor element. An arrangement of the segments is processed by a neural network; the neural network includes at least one attention layer. Based on the processed segment a probability model is obtained for entropy encoding or decoding of a latent tensor element.

公开(公告)号：US20230116285A1

公开(公告)日：2023-04-13

申请号：US18064745

申请日：2022-12-12

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Kai Cui ,  Atanas Boev ,  Elena Alexandrovna Alshina ,  Eckehard Steinbach

IPC: H04N19/88 ,  H04N19/436 ,  H04N19/167 ,  H04N19/186 ,  H04N19/136 ,  H04N19/17

Abstract: The present disclosure relates to image modification such as an image enhancement. The image enhancement may be applied for any image modification and it may be applied during or after image encoding and/or decoding, e.g. as a loop filter or a post filter. In particular, the image modification includes a multi-channel processing in which a primary channel is processed separately and secondary channels are processed based on the processed primary channel. The processing is based on a neural network. In order to enhance the image modification performance, prior to applying the modification, the image channels are analyzed and a primary channel and the secondary channels are determined, which may vary for multiples of images, images or image areas.

公开(公告)号：US11049472B2

公开(公告)日：2021-06-29

申请号：US16752965

申请日：2020-01-27

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Atanas Boev ,  Panji Setiawan

IPC: G09G5/02 ,  G02B30/26 ,  G02B27/01 ,  G02F1/1335 ,  G09G3/36

Abstract: The disclosure provides a multifocal display device, comprising a display configured to generate an image, and a controller configured to control the display according to a bit sequence provided over a determined time period to generate the image with one or more colors. The bit sequence includes for each color a subsequence of bits of different significance. Neither the first bit nor the last bit of the subsequence for the respective color is the most significant bit of the subsequence.

公开(公告)号：US20250142066A1

公开(公告)日：2025-05-01

申请号：US19007327

申请日：2024-12-31

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Johannes Sauer ,  Panqi Jia ,  Elena Alexandrovna Alshina ,  Atanas Boev

IPC: H04N19/119 ,  H04N19/176 ,  H04N19/186

Abstract: The present disclosure relates to picture encoding and decoding of image regions on tile-basis. In particular, multiple components of an input tensor including a first and second component in spatial dimensions is processed within multiple pipelines. The processing of the first component includes dividing the first component in the spatial dimensions into a first plurality of tiles. Likewise, the processing of the second component includes dividing the second component in the spatial dimensions into a second plurality of tiles. The respective first and second plurality of tiles are then processed each separately. Among the first and second plurality of tiles there are at least two respective collocated tiles differing in size. In case of compression, the processing of the first and/or second component includes picture encoding, rate distortion optimization quantization, and picture filtering. In case of decompression, the processing includes picture decoding and picture filtering.

公开(公告)号：US20240078414A1

公开(公告)日：2024-03-07

申请号：US18507949

申请日：2023-11-13

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Ahmet Burakhan Koyuncu ,  Atanas Boev ,  Elena Alexandrovna Alshina

IPC: G06N3/0464 ,  G06N7/01

CPC classification number: G06N3/0464 ,  G06N7/01

Abstract: Methods and apparatuses are provided for entropy encoding and decoding of a latent tensor, which includes separating the latent tensor into patches and obtaining a probability model for the entropy encoding of a current element of the latent tensor by processing a set of elements from different patches by one or more layers of a neural network. The processing of the set of elements by applying a convolution kernel enables sharing of information between the separated patches.

公开(公告)号：US11726346B2

公开(公告)日：2023-08-15

申请号：US17461501

申请日：2021-08-30

Applicant: Huawei Technologies Co., Ltd.

Inventor： Hector Navarro Fructuoso ,  Atanas Boev ,  Panji Setiawan ,  Onay Urfalioglu

IPC: G02B27/00 ,  G02B30/40 ,  H04N13/167 ,  H04N13/144 ,  H04N13/351 ,  H04N13/398 ,  G02B7/06

CPC classification number: G02B30/40 ,  G02B7/06 ,  H04N13/144 ,  H04N13/167 ,  H04N13/351 ,  H04N13/398

Abstract: A focus tunable optical system includes a compound lens, which includes a plurality of focus tunable lenses. Further, the focus tunable optical system comprises a controller, which is configured to shift a focus of the compound lens from a first focal plane to a second focal plane. To this end, the controller is configured to apply, individually to each focus tunable lens of the plurality of the focus tunable lenses, a control signal having a first value for the first focal plane and a second value for the second focal plane.

公开(公告)号：US11662547B2

公开(公告)日：2023-05-30

申请号：US16741849

申请日：2020-01-14

Applicant: Huawei Technologies Co., Ltd.

Inventor： Atanas Boev ,  Panji Setiawan

IPC: G02B7/09 ,  G02B30/52

CPC classification number: G02B7/09 ,  G02B30/52

Abstract: A multifocal display device has a focus tunable lens, a controller, and a storage. The controller selectively tunes the focus of the lens to a plurality of focal planes of different index during a frame per A focal plane of lower index has a shorter focal distance. The storage stores a plurality of focal plane groups, each group including the plurality of focal planes in a different sequence. The controller selects a first group and tunes, during a first frame period, the focus of the lens to each one of the focal planes in the first group according to their sequence, and selects a second group from groups allowed by a selection rule, and tunes, during a second frame period, the focus of the lens to each one of the focal planes in the second group according to their sequence.

公开(公告)号：US12047613B2

公开(公告)日：2024-07-23

申请号：US18064745

申请日：2022-12-12

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Kai Cui ,  Atanas Boev ,  Elena Alexandrovna Alshina ,  Eckehard Steinbach

IPC: H04N19/88 ,  H04N19/136 ,  H04N19/167 ,  H04N19/17 ,  H04N19/186 ,  H04N19/436

CPC classification number: H04N19/88 ,  H04N19/136 ,  H04N19/167 ,  H04N19/17 ,  H04N19/186 ,  H04N19/436

Abstract: The present disclosure relates to image modification such as an image enhancement. The image enhancement may be applied for any image modification and it may be applied during or after image encoding and/or decoding, e.g. as a loop filter or a post filter. In particular, the image modification includes a multi-channel processing in which a primary channel is processed separately and secondary channels are processed based on the processed primary channel. The processing is based on a neural network. In order to enhance the image modification performance, prior to applying the modification, the image channels are analyzed and a primary channel and the secondary channels are determined, which may vary for multiples of images, images or image areas.

公开(公告)号：US11470289B2

公开(公告)日：2022-10-11

申请号：US17140808

申请日：2021-01-04

Applicant: Huawei Technologies Co., Ltd.

Inventor： Hector Navarro Fructuoso ,  Bogdan Cihodariu Ionita ,  Atanas Boev ,  Panji Setiawan

IPC: H04N9/31 ,  G02B27/01 ,  G06F3/01

Abstract: The disclosure relates to a retinal display apparatus for generating an image on the retina of an eye of a user, wherein the retinal display apparatus is configured to generate multiple light beams, each light beam conveying an instance of the image, wherein the multiple light beams correspond one-to-one to multiple potential orientations of the eye of the user. Moreover, the disclosure relates to a corresponding method.

公开(公告)号：US11106052B2

公开(公告)日：2021-08-31

申请号：US16844841

申请日：2020-04-09

Applicant: Huawei Technologies Co., Ltd.

Inventor： Hector Navarro Fructuoso ,  Atanas Boev ,  Panji Setiawan ,  Onay Urfalioglu

IPC: G02B27/00 ,  G02B30/40 ,  G02B3/14 ,  G02B7/06 ,  H04N13/144 ,  H04N13/167 ,  H04N13/351 ,  H04N13/398

Abstract: A focus tunable optical system includes a compound lens, which includes a plurality of focus tunable lenses. Further, the focus tunable optical system includes a controller, which is configured to shift a focus of the compound lens from a first focal plane to a second focal plane. To this end, the controller is configured to apply, individually to each focus tunable lens of the plurality of the focus tunable lenses, a control signal having a first value for the first focal plane and a second value for the second focal plane.